Past Traffic Intelligence news
Traffic Intelligence is my main repository for research, with various tools for transport data management, in particular trajectory extraction from video data for road user behavior and safety analysis.
Since it is difficult to post updates and have people find them, I will now post updates here, where people can subscribe to updates for the particular traffic-intelligence tag.
For completeness, here are the past news from the repository:
- October 2023: a new script, dltrack.py, has been developed to take advantage of the deep learning models available in ultralytics to classify and track road users. More documentation to come.
- July 1st 2021: the Linux repository version of the OpenCV library (tested on Ubuntu) is sufficient to compile the tracker.
- After Bitbucket shut down mercurial repositories in the Summer of 2020, here are the solutions I found. I strongly prefer Mercurial to Git, so will keep the code in this version control system. I will keep this repository to link things and put the documentation back up in the main repository in the docs sub-directory.
- Main Traffic Intelligence Mercurial repository.
- The Trajectory management and analysis tool project used to be separately hosted and is now integrated in the main Traffic Intelligence repository after Btibucket gave up on Mercurial.
- February 2nd 2019: The C++ code has been updated to OpenCV4 (you also need to update the trajectory management and analysis library). Python code seem to need no update as tests are passed.
- June 15th 2018: The Python code is now put in a trafficintelligence package (namespace) and can be installed in your Python dist-packages using pip.
- June 13th 2018: Re-uploading the Laurier sample data and adding an example of videor with lens distortion, plus a metadata.sqlite file
- May 27th 2018: Brand new version with latest OpenCV3 and Python3 support. Please report bugs!
- June 10th 2016: after initially switching to OpenCV3 (v3.1), we have backtracked (most recent v2.4.13) since there are issues with loading SVM classifiers. The current default version also includes changes in the tracking configuration file, moving the classification parameters to a new classifier.cfg file and making all parameters apparent there (they were hidden, ie default values in the code, previously).
- August 7th 2015: the script computer-clearmot.py now has the functionality to display the matches, missed ground truth instants and tracking false alarm with the --display option (and --mask if you want to restrict tracking to the mask used for annotations).
- July 25th 2015: major news as Adrien Lessard, undergrad student, found that indexing one database accelerates by orders of magnitude the feature grouping, and I have finally found an old bug that had eluded so far. The result is several orders of magnitude faster (but only for grouping)!
- July 21st 2015: after some cleaning of the C++ code (updating to C++11 and removing functionalities provided by OpenCV such as reading sets of images as videos), the new Windows binary is available. Also, road user classifiers are now available in the dev branch of the code.
- March 24th 2015: added more details on the use of the
compute-homography.pyscript in the camera calibration tutorial - June 4th 2014: added functionality to deal with radial distortion (aka fish eye effect, eg from GoPro cameras). This means that more parameters are needed in the configuration file. The file cannot be updated automatically, see How to update configuration files for solutions.